Skip to content

Instantly share code, notes, and snippets.

Last active January 24, 2021 15:06
Show Gist options
  • Save scrapehero/1c425fdf290144cd4c7c635587feb459 to your computer and use it in GitHub Desktop.
Save scrapehero/1c425fdf290144cd4c7c635587feb459 to your computer and use it in GitHub Desktop.
Python Script to scrape for Hotels in a locality. Code Written as part of
#!/usr/bin/env python
from datetime import datetime
from time import time
from lxml import html,etree
import requests,re
import os,sys
import unicodecsv as csv
import argparse
def parse(locality,checkin_date,checkout_date,sort):
checkIn = checkin_date.strftime("%Y/%m/%d")
checkOut = checkout_date.strftime("%Y/%m/%d")
print "Scraper Inititated for Locality:%s"%locality
# TA rendering the autocomplete list using this API
print "Finding search result page URL"
geo_url = ''+str(int(time()))+'&uiOrigin=GEOSCOPE&source=GEOSCOPE&interleaved=true&types=geo,theme_park&neighborhood_geos=true&link_type=hotel&details=true&max=12&injectNeighborhoods=true&query='+locality
api_response = requests.get(geo_url, verify=False).json()
#getting the TA url for th equery from the autocomplete response
url_from_autocomplete = ""+api_response['results'][0]['url']
print 'URL found %s'%url_from_autocomplete
geo = api_response['results'][0]['value']
#Formating date for writing to file
date = checkin_date.strftime("%Y_%m_%d")+"_"+checkout_date.strftime("%Y_%m_%d")
#form data to get the hotels list from TA for the selected date
form_data = {'changeSet': 'TRAVEL_INFO',
'showSnippets': 'false',
'uguests': '2',
#Referrer is necessary to get the correct response from TA if not provided they will redirect to home page
headers = {
'Accept': 'text/javascript, text/html, application/xml, text/xml, */*',
'Accept-Encoding': 'gzip,deflate',
'Accept-Language': 'en-US,en;q=0.5',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
'Host': '',
'Pragma': 'no-cache',
'Referer': url_from_autocomplete,
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:28.0) Gecko/20100101 Firefox/28.0',
'X-Requested-With': 'XMLHttpRequest'
cookies= {"SetCurrency":"USD"}
print "Downloading search results page"
page_response = = url_from_autocomplete,data=form_data,headers = headers, cookies = cookies, verify=False)
print "Parsing results "
parser = html.fromstring(page_response.text)
hotel_lists = parser.xpath('//div[contains(@class,"listItem")]//div[contains(@class,"listing collapsed")]')
hotel_data = []
if not hotel_lists:
hotel_lists = parser.xpath('//div[contains(@class,"listItem")]//div[@class="listing "]')
for hotel in hotel_lists:
XPATH_HOTEL_LINK = './/a[contains(@class,"property_title")]/@href'
XPATH_REVIEWS = './/a[@class="review_count"]//text()'
XPATH_RANK = './/div[@class="popRanking"]//text()'
XPATH_RATING = './/span[contains(@class,"rating")]/@alt'
XPATH_HOTEL_NAME = './/a[contains(@class,"property_title")]//text()'
XPATH_HOTEL_FEATURES = './/div[contains(@class,"common_hotel_icons_list")]//li//text()'
XPATH_HOTEL_PRICE = './/div[contains(@data-sizegroup,"mini-meta-price")]/text()'
XPATH_VIEW_DEALS = './/div[contains(@data-ajax-preserve,"viewDeals")]//text()'
XPATH_BOOKING_PROVIDER = './/div[contains(@data-sizegroup,"mini-meta-provider")]//text()'
raw_booking_provider = hotel.xpath(XPATH_BOOKING_PROVIDER)
raw_no_of_deals = hotel.xpath(XPATH_VIEW_DEALS)
raw_hotel_link = hotel.xpath(XPATH_HOTEL_LINK)
raw_no_of_reviews = hotel.xpath(XPATH_REVIEWS)
raw_rank = hotel.xpath(XPATH_RANK)
raw_rating = hotel.xpath(XPATH_RATING)
raw_hotel_name = hotel.xpath(XPATH_HOTEL_NAME)
raw_hotel_features = hotel.xpath(XPATH_HOTEL_FEATURES)
raw_hotel_price_per_night = hotel.xpath(XPATH_HOTEL_PRICE)
url = ''+raw_hotel_link[0] if raw_hotel_link else None
reviews = ''.join(raw_no_of_reviews).replace("reviews","").replace(",","") if raw_no_of_reviews else 0
rank = ''.join(raw_rank) if raw_rank else None
rating = ''.join(raw_rating).replace('of 5 bubbles','').strip() if raw_rating else None
name = ''.join(raw_hotel_name).strip() if raw_hotel_name else None
hotel_features = ','.join(raw_hotel_features)
price_per_night = ''.join(raw_hotel_price_per_night).encode('utf-8').replace('\n','') if raw_hotel_price_per_night else None
no_of_deals = re.findall("all\s+?(\d+)\s+?",''.join(raw_no_of_deals))
booking_provider = ''.join(raw_booking_provider).strip() if raw_booking_provider else None
if no_of_deals:
no_of_deals = no_of_deals[0]
no_of_deals = 0
data = {
return hotel_data
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('checkin_date',help = 'Hotel Check In Date (Format: YYYY/MM/DD')
parser.add_argument('checkout_date',help = 'Hotel Chek Out Date (Format: YYYY/MM/DD)')
sortorder_help = """
available sort orders are :\n
priceLow - hotels with lowest price,
distLow : Hotels located near to the search center,
recommended: highest rated hotels based on traveler reviews,
popularity :Most popular hotels as chosen by Tipadvisor users
parser.add_argument('sort',help = sortorder_help,default ='popularity ')
parser.add_argument('locality',help = 'Search Locality')
args = parser.parse_args()
locality = args.locality
checkin_date = datetime.strptime(args.checkin_date,"%Y/%m/%d")
checkout_date = datetime.strptime(args.checkout_date,"%Y/%m/%d")
sort= args.sort
checkIn = checkin_date.strftime("%Y/%m/%d")
checkOut = checkout_date.strftime("%Y/%m/%d")
today =
if today<datetime.strptime(checkIn,"%Y/%m/%d") and datetime.strptime(checkIn,"%Y/%m/%d")<datetime.strptime(checkOut,"%Y/%m/%d"):
data = parse(locality,checkin_date,checkout_date,sort)
print "Writing to output file tripadvisor_data.csv"
with open('tripadvisor_data.csv','w')as csvfile:
fieldnames = ['hotel_name','url','locality','reviews','tripadvisor_rating','checkIn','checkOut','price_per_night','booking_provider','no_of_deals','hotel_features']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
for row in data:
#checking whether the entered date is already passed
elif today>datetime.strptime(checkIn,"%Y/%m/%d") or today>datetime.strptime(checkOut,"%Y/%m/%d"):
print "Invalid Checkin date: Please enter a valid checkin and checkout dates,entered date is already passed"
elif datetime.strptime(checkIn,"%Y/%m/%d")>datetime.strptime(checkOut,"%Y/%m/%d"):
print "Invalid Checkin date: CheckIn date must be less than checkOut date"
Copy link

JDKao commented Sep 19, 2017

Cant use anymore.
Output CSV nothing inside.

Copy link

Unfortunatelly is not working anymore, does anyone has the fix?

Copy link

The site had changed their front-end slightly. We have now modified the code.

Copy link

botsbuzz commented May 6, 2018

CSV is empty for me. Any idea to fix that?

Copy link

Fixed now.

Copy link

ghost commented Aug 23, 2018

it is not working csv is empty

Copy link

JujuD28 commented Nov 24, 2018

I have the following error : TypeError: a bytes-like object is required, not 'str'

Copy link

s4lmon commented Mar 17, 2019

I have the following error : TypeError: a bytes-like object is required, not 'str'

This script can be fixed by modifying line 83 as follows:

price_per_night = ''.join(raw_hotel_price_per_night).replace('\n','') if raw_hotel_price_per_night else None

I have this running on Python 3 by only modifying this and adding brackets to the print statements.

Copy link

The code seems to skip hotels that show up in the search, every sixth hotel is saved in the csv - any suggestions?

Copy link

zmfink commented Jul 25, 2019

It also appears that on first call, many of the prices are not returning. Although, if you run the same command a second time (exact same arguments), then all prices return. Is there a way to get all prices on first call?

Copy link

hgayanj commented Feb 24, 2020

it works fine after few modifications suggested above but the rating column is blank and adding to that it only provide the search results of 1st page. how can i go to next pages and get results?

Copy link

I've got an error :

Parsing results
Writing to output file tripadvisor_data.csv
Traceback (most recent call last):
  File "", line 144, in <module>
  File "c:\anaconda3\lib\site-packages\unicodecsv\", line 85, in writeheader
  File "C:\Anaconda3\lib\", line 155, in writerow
    return self.writer.writerow(self._dict_to_list(rowdict))
  File "c:\anaconda3\lib\site-packages\unicodecsv\", line 28, in writerow
    return self.writer.writerow(row)
  File "c:\anaconda3\lib\site-packages\unicodecsv\", line 15, in write
    return self.binary.write(string.encode(self.encoding, self.errors))
TypeError: write() argument must be str, not bytes

Any idea how to fix it?

Copy link

#getting the TA url for th equery from the autocomplete response
url_from_autocomplete = ""+api_response['results'][0]['url']
print 'URL found %s'%url_from_autocomplete
geo = api_response['results'][0]['value']

for this piece of code i am getting list index out of range.
can any one help please.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment